2019
DOI: 10.1016/j.microrel.2019.06.077
|View full text |Cite
|
Sign up to set email alerts
|

Approximate TMR based on successive approximation and loop perforation in microprocessors

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
13
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
3
3
1

Relationship

1
6

Authors

Journals

citations
Cited by 15 publications
(13 citation statements)
references
References 5 publications
0
13
0
Order By: Relevance
“…In summary, input vectors for which only two out of three AxICs compute correctly are not protected against faults. A possible alternative to mitigate the problem is to adopt a modified checker that computes the average of the results, as proposed in [18] for a software ATMR implementation. However, in this case the outputs are approximate (i.e., not precise).…”
Section: Approximation-based Fault Tolerancementioning
confidence: 99%
“…In summary, input vectors for which only two out of three AxICs compute correctly are not protected against faults. A possible alternative to mitigate the problem is to adopt a modified checker that computes the average of the results, as proposed in [18] for a software ATMR implementation. However, in this case the outputs are approximate (i.e., not precise).…”
Section: Approximation-based Fault Tolerancementioning
confidence: 99%
“…Approximate TMR (ATMR) is based on implementing each redundancy task with a different architecture or algorithm [35]. When applied to hardware projects, ATMR has been presented as a way to achieve fault coverage almost as good as traditional TMR but avoiding the huge area overhead that it costs [36].…”
Section: Approximation and Fault Tolerancementioning
confidence: 99%
“…The ATMR technique proposed in [30] is not restricted by mathematical constraints and utilizes the notion of approximation intensity and successive approximation. Through successive approximation algorithms, with each loop, output quality is iteratively improved.…”
Section: ) Atmr Based On Successive Approximation and Loop Perforatio...mentioning
confidence: 99%
“…For instance, the Newton-Raphson benchmark successively approximates to compute the roots of the function. This algorithm is used as a benchmark application in [30]. FIGURE 9.…”
Section: ) Atmr Based On Successive Approximation and Loop Perforatio...mentioning
confidence: 99%